We propose MomentsNeRF, a novel framework for one- and few-shot neural
rendering that predicts a neural representation of a 3D scene using Orthogonal
Moments. Our architecture offers a new transfer learning method to train on
multi-scenes and incorporate a per-scene optimization using one or a few images
at test time. Our approach is the first to successfully harness features
extracted from Gabor and Zernike moments, seamlessly integrating them into the
NeRF architecture. We show that MomentsNeRF performs better in synthesizing
images with complex textures and shapes, achieving a significant noise
reduction, artifact elimination, and completing the missing parts compared to
the recent one- and few-shot neural rendering frameworks. Extensive experiments
on the DTU and Shapenet datasets show that MomentsNeRF improves the
state-of-the-art by {3.39\;dB\;PSNR}, 11.1% SSIM, 17.9% LPIPS, and 8.3% DISTS
metrics. Moreover, it outperforms state-of-the-art performance for both novel
view synthesis and single-image 3D view reconstruction. The source code is
accessible at: this https URL

提出了 MomentsNeRF，一种新的一次和少量次一次性神经渲染框架，使用正交矩计算预测三维场景的神经表示。在合成具有复杂纹理和形状的图像方面，MomentsNeRF 表现更好，实现了显著的噪声降低、伪影消除和填补缺失部分，超越了最近的一次和少量次神经渲染框架的能力。在 DTU 和 Shapenet 数据集上进行了大量实验，MomentsNeRF 在 PSNR（3.39 dB）、SSIM（11.1%）、LPIPS（17.9%）和 DISTS（8.3%）等指标方面改进了最先进的技术，并且在新视角合成和单图像三维视图重构方面表现出色。源代码可在此链接获取。